Music scale modeling for melody matching

Abstract

Several time series matching techniques have been proposed for content-based music retrieval. These techniques represent a melody by a time series of pitch values and use time warping distance measures for melody matching. These methods have shown to be robust and effective for music retrieval by acoustic inputs, such as query-by-humming. However, due to the key transposition issue, all the current methods need to search a large space for the proper key in melody matching. This computation can be prohibitive for a practical music retrieval system with a large database.In this paper, we present a music scale modeling technique for melody matching. The root note of music scale (Major or Minor) of a melody is estimated by fitting the notes to a music scale model. The estimated root note can then be used as the key in melody matching. To the best of our knowledge, this is the first approach that utilizes music scale knowledge for retrieval. In our experiments, 96% of the songs in the database (3000 melodies) can fit into the music scale model. Promising results for query-by-humming retrieval have been obtained by using this novel approach.

Real-Time Maqam Estimation Model in Max/MSP Configured for the Nāy

“…Each scale is identified by the pitch intervals between the sequence of notes in one octave, and recurring in all upper or lower octaves [16] [17]. Arab maqamat are better to be studied and described in the context of the arab musical heritage, but the closest counterpart from the occidental music might be the mode [18], particularly, the Greek modes.…”

Compacting music signatures for efficient music retrieval

“…The second class adopts symbolic representation based on the musical scores and notes in the score to keep track of musical information such as tone, pitch and duration. In this case, the problem of music retrieval can be transformed into approximate string matching or time sequence/series data matching [9,10,15,18,25,26,30,31]. Unfortunately, these algorithms are computationally expensive (and hence impractical) for large music databases as the entirety of a database has to be scanned to find matching sequences for each query.…”

“…We compare against q-gram method [6,27], and we set q equal to 3. We also compare our method with sequence similarity matching methods [18,30,31]. With the melodies properly transposed, a sequence similarity measure can be used for melody matching, and time warping distance can be a good similarity measurement.…”

Key, Chord, and Rhythm Tracking of Popular Music Recordings

“…Existing work in key determination has been restricted to either the symbolic domain (MIDI and score), or, in the audio domain, single-instrument and simple polyphonic sounds (see for example, Ng et al 1996;Chew 2001Chew , 2002Povel 2002;Pickens 2003;Raphael and Stoddard 2003;Zhu and Kankanhalli 2003;Zhu et al 2004). A system to extract the musical key from classical piano sonatas sampled from compact discs has been demonstrated by Pauws (2004).…”